in kernel/setup.c [756:1228]
void __init setup_arch(char **cmdline_p)
{
#ifdef CONFIG_X86_32
memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
/*
* copy kernel address range established so far and switch
* to the proper swapper page table
*/
clone_pgd_range(swapper_pg_dir + KERNEL_PGD_BOUNDARY,
initial_page_table + KERNEL_PGD_BOUNDARY,
KERNEL_PGD_PTRS);
load_cr3(swapper_pg_dir);
/*
* Note: Quark X1000 CPUs advertise PGE incorrectly and require
* a cr3 based tlb flush, so the following __flush_tlb_all()
* will not flush anything because the CPU quirk which clears
* X86_FEATURE_PGE has not been invoked yet. Though due to the
* load_cr3() above the TLB has been flushed already. The
* quirk is invoked before subsequent calls to __flush_tlb_all()
* so proper operation is guaranteed.
*/
__flush_tlb_all();
#else
printk(KERN_INFO "Command line: %s\n", boot_command_line);
boot_cpu_data.x86_phys_bits = MAX_PHYSMEM_BITS;
#endif
/*
* If we have OLPC OFW, we might end up relocating the fixmap due to
* reserve_top(), so do this before touching the ioremap area.
*/
olpc_ofw_detect();
idt_setup_early_traps();
early_cpu_init();
jump_label_init();
static_call_init();
early_ioremap_init();
setup_olpc_ofw_pgd();
ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
screen_info = boot_params.screen_info;
edid_info = boot_params.edid_info;
#ifdef CONFIG_X86_32
apm_info.bios = boot_params.apm_bios_info;
ist_info = boot_params.ist_info;
#endif
saved_video_mode = boot_params.hdr.vid_mode;
bootloader_type = boot_params.hdr.type_of_loader;
if ((bootloader_type >> 4) == 0xe) {
bootloader_type &= 0xf;
bootloader_type |= (boot_params.hdr.ext_loader_type+0x10) << 4;
}
bootloader_version = bootloader_type & 0xf;
bootloader_version |= boot_params.hdr.ext_loader_ver << 4;
#ifdef CONFIG_BLK_DEV_RAM
rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK;
#endif
#ifdef CONFIG_EFI
if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
EFI32_LOADER_SIGNATURE, 4)) {
set_bit(EFI_BOOT, &efi.flags);
} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
EFI64_LOADER_SIGNATURE, 4)) {
set_bit(EFI_BOOT, &efi.flags);
set_bit(EFI_64BIT, &efi.flags);
}
#endif
x86_init.oem.arch_setup();
/*
* Do some memory reservations *before* memory is added to memblock, so
* memblock allocations won't overwrite it.
*
* After this point, everything still needed from the boot loader or
* firmware or kernel text should be early reserved or marked not RAM in
* e820. All other memory is free game.
*
* This call needs to happen before e820__memory_setup() which calls the
* xen_memory_setup() on Xen dom0 which relies on the fact that those
* early reservations have happened already.
*/
early_reserve_memory();
iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
e820__memory_setup();
parse_setup_data();
copy_edd();
if (!boot_params.hdr.root_flags)
root_mountflags &= ~MS_RDONLY;
setup_initial_init_mm(_text, _etext, _edata, (void *)_brk_end);
code_resource.start = __pa_symbol(_text);
code_resource.end = __pa_symbol(_etext)-1;
rodata_resource.start = __pa_symbol(__start_rodata);
rodata_resource.end = __pa_symbol(__end_rodata)-1;
data_resource.start = __pa_symbol(_sdata);
data_resource.end = __pa_symbol(_edata)-1;
bss_resource.start = __pa_symbol(__bss_start);
bss_resource.end = __pa_symbol(__bss_stop)-1;
#ifdef CONFIG_CMDLINE_BOOL
#ifdef CONFIG_CMDLINE_OVERRIDE
strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
#else
if (builtin_cmdline[0]) {
/* append boot loader cmdline to builtin */
strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
}
#endif
#endif
strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
*cmdline_p = command_line;
/*
* x86_configure_nx() is called before parse_early_param() to detect
* whether hardware doesn't support NX (so that the early EHCI debug
* console setup can safely call set_fixmap()). It may then be called
* again from within noexec_setup() during parsing early parameters
* to honor the respective command line option.
*/
x86_configure_nx();
parse_early_param();
if (efi_enabled(EFI_BOOT))
efi_memblock_x86_reserve_range();
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* Memory used by the kernel cannot be hot-removed because Linux
* cannot migrate the kernel pages. When memory hotplug is
* enabled, we should prevent memblock from allocating memory
* for the kernel.
*
* ACPI SRAT records all hotpluggable memory ranges. But before
* SRAT is parsed, we don't know about it.
*
* The kernel image is loaded into memory at very early time. We
* cannot prevent this anyway. So on NUMA system, we set any
* node the kernel resides in as un-hotpluggable.
*
* Since on modern servers, one node could have double-digit
* gigabytes memory, we can assume the memory around the kernel
* image is also un-hotpluggable. So before SRAT is parsed, just
* allocate memory near the kernel image to try the best to keep
* the kernel away from hotpluggable memory.
*/
if (movable_node_is_enabled())
memblock_set_bottom_up(true);
#endif
x86_report_nx();
if (acpi_mps_check()) {
#ifdef CONFIG_X86_LOCAL_APIC
disable_apic = 1;
#endif
setup_clear_cpu_cap(X86_FEATURE_APIC);
}
e820__reserve_setup_data();
e820__finish_early_params();
if (efi_enabled(EFI_BOOT))
efi_init();
dmi_setup();
/*
* VMware detection requires dmi to be available, so this
* needs to be done after dmi_setup(), for the boot CPU.
*/
init_hypervisor_platform();
tsc_early_init();
x86_init.resources.probe_roms();
/* after parse_early_param, so could debug it */
insert_resource(&iomem_resource, &code_resource);
insert_resource(&iomem_resource, &rodata_resource);
insert_resource(&iomem_resource, &data_resource);
insert_resource(&iomem_resource, &bss_resource);
e820_add_kernel_range();
trim_bios_range();
#ifdef CONFIG_X86_32
if (ppro_with_ram_bug()) {
e820__range_update(0x70000000ULL, 0x40000ULL, E820_TYPE_RAM,
E820_TYPE_RESERVED);
e820__update_table(e820_table);
printk(KERN_INFO "fixed physical RAM map:\n");
e820__print_table("bad_ppro");
}
#else
early_gart_iommu_check();
#endif
/*
* partially used pages are not usable - thus
* we are rounding upwards:
*/
max_pfn = e820__end_of_ram_pfn();
/* update e820 for memory not covered by WB MTRRs */
if (IS_ENABLED(CONFIG_MTRR))
mtrr_bp_init();
else
pat_disable("PAT support disabled because CONFIG_MTRR is disabled in the kernel.");
if (mtrr_trim_uncached_memory(max_pfn))
max_pfn = e820__end_of_ram_pfn();
max_possible_pfn = max_pfn;
/*
* This call is required when the CPU does not support PAT. If
* mtrr_bp_init() invoked it already via pat_init() the call has no
* effect.
*/
init_cache_modes();
/*
* Define random base addresses for memory sections after max_pfn is
* defined and before each memory section base is used.
*/
kernel_randomize_memory();
#ifdef CONFIG_X86_32
/* max_low_pfn get updated here */
find_low_pfn_range();
#else
check_x2apic();
/* How many end-of-memory variables you have, grandma! */
/* need this before calling reserve_initrd */
if (max_pfn > (1UL<<(32 - PAGE_SHIFT)))
max_low_pfn = e820__end_of_low_ram_pfn();
else
max_low_pfn = max_pfn;
high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
#endif
/*
* Find and reserve possible boot-time SMP configuration:
*/
find_smp_config();
early_alloc_pgt_buf();
/*
* Need to conclude brk, before e820__memblock_setup()
* it could use memblock_find_in_range, could overlap with
* brk area.
*/
reserve_brk();
cleanup_highmap();
memblock_set_current_limit(ISA_END_ADDRESS);
e820__memblock_setup();
/*
* Needs to run after memblock setup because it needs the physical
* memory size.
*/
sev_setup_arch();
efi_fake_memmap();
efi_find_mirror();
efi_esrt_init();
efi_mokvar_table_init();
/*
* The EFI specification says that boot service code won't be
* called after ExitBootServices(). This is, in fact, a lie.
*/
efi_reserve_boot_services();
/* preallocate 4k for mptable mpc */
e820__memblock_alloc_reserved_mpc_new();
#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
setup_bios_corruption_check();
#endif
#ifdef CONFIG_X86_32
printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n",
(max_pfn_mapped<<PAGE_SHIFT) - 1);
#endif
/*
* Find free memory for the real mode trampoline and place it there. If
* there is not enough free memory under 1M, on EFI-enabled systems
* there will be additional attempt to reclaim the memory for the real
* mode trampoline at efi_free_boot_services().
*
* Unconditionally reserve the entire first 1M of RAM because BIOSes
* are known to corrupt low memory and several hundred kilobytes are not
* worth complex detection what memory gets clobbered. Windows does the
* same thing for very similar reasons.
*
* Moreover, on machines with SandyBridge graphics or in setups that use
* crashkernel the entire 1M is reserved anyway.
*/
reserve_real_mode();
init_mem_mapping();
idt_setup_early_pf();
/*
* Update mmu_cr4_features (and, indirectly, trampoline_cr4_features)
* with the current CR4 value. This may not be necessary, but
* auditing all the early-boot CR4 manipulation would be needed to
* rule it out.
*
* Mask off features that don't work outside long mode (just
* PCIDE for now).
*/
mmu_cr4_features = __read_cr4() & ~X86_CR4_PCIDE;
memblock_set_current_limit(get_max_mapped());
/*
* NOTE: On x86-32, only from this point on, fixmaps are ready for use.
*/
#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
if (init_ohci1394_dma_early)
init_ohci1394_dma_on_all_controllers();
#endif
/* Allocate bigger log buffer */
setup_log_buf(1);
if (efi_enabled(EFI_BOOT)) {
switch (boot_params.secure_boot) {
case efi_secureboot_mode_disabled:
pr_info("Secure boot disabled\n");
break;
case efi_secureboot_mode_enabled:
pr_info("Secure boot enabled\n");
break;
default:
pr_info("Secure boot could not be determined\n");
break;
}
}
reserve_initrd();
acpi_table_upgrade();
/* Look for ACPI tables and reserve memory occupied by them. */
acpi_boot_table_init();
vsmp_init();
io_delay_init();
early_platform_quirks();
early_acpi_boot_init();
initmem_init();
dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT);
if (boot_cpu_has(X86_FEATURE_GBPAGES))
hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
/*
* Reserve memory for crash kernel after SRAT is parsed so that it
* won't consume hotpluggable memory.
*/
reserve_crashkernel();
memblock_find_dma_reserve();
if (!early_xdbc_setup_hardware())
early_xdbc_register_console();
x86_init.paging.pagetable_init();
kasan_init();
/*
* Sync back kernel address range.
*
* FIXME: Can the later sync in setup_cpu_entry_areas() replace
* this call?
*/
sync_initial_page_table();
tboot_probe();
map_vsyscall();
generic_apic_probe();
early_quirks();
/*
* Read APIC and some other early information from ACPI tables.
*/
acpi_boot_init();
x86_dtb_init();
/*
* get boot-time SMP configuration:
*/
get_smp_config();
/*
* Systems w/o ACPI and mptables might not have it mapped the local
* APIC yet, but prefill_possible_map() might need to access it.
*/
init_apic_mappings();
prefill_possible_map();
init_cpu_to_node();
init_gi_nodes();
io_apic_init_mappings();
x86_init.hyper.guest_late_init();
e820__reserve_resources();
e820__register_nosave_regions(max_pfn);
x86_init.resources.reserve_resources();
e820__setup_pci_gap();
#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
conswitchp = &vga_con;
#endif
#endif
x86_init.oem.banner();
x86_init.timers.wallclock_init();
/*
* This needs to run before setup_local_APIC() which soft-disables the
* local APIC temporarily and that masks the thermal LVT interrupt,
* leading to softlockups on machines which have configured SMI
* interrupt delivery.
*/
therm_lvt_init();
mcheck_init();
register_refined_jiffies(CLOCK_TICK_RATE);
#ifdef CONFIG_EFI
if (efi_enabled(EFI_BOOT))
efi_apply_memmap_quirks();
#endif
unwind_init();
}